Process capability for non normal data

Six Sigma – iSixSigma Forums Old Forums General Process capability for non normal data

Viewing 2 posts - 1 through 2 (of 2 total)
  • Author
  • #32202


    I have to carry out a process capability with non normal data. They refer to days of delay in delivery some documents. I’m thinking to use a capability index like this:
    where Up and Lp are the percentiles 99.865% and 0.135% respectively.
    Cpk=min((USL-Median)/(Up-Median); (Median-Lp)/(Median-Lp))
    I’d like to know if in your opinion it is correct or there’s an easier way to estimate the capability of my process. Furthermore I ask you if there’s any limitation to the use of this index.
    Many thanks to all you,


    Robert Butler

      Your proposal looks to be in agreement with Chapter 8 – Capability for Non-Normal Data in Bothe’s book Measuring Process Capability.  From that standpoint it would appear that you are correct.  According to Bothe (pp.438) the drawbacks are as follows:
    “However, on account of the units of measurements associated with this measure (the equivalent 6 sigma long term spread) the equivalent 6 sigma long term for one type of process cannot easily be compared to the equivalent 6 sigma long term of another.”
    ” Another disadvantage is that meeasurement data must be plotted on NOPP to determint the percentiles, which does require some time.”

Viewing 2 posts - 1 through 2 (of 2 total)

The forum ‘General’ is closed to new topics and replies.